האם סוכני פעולה פרואקטיביים צריכים LLM להחלטה כשלהם לפעול?

תקציר מקורי באנגליתarXiv:2605.30152v2 Announce Type: replace-cross Abstract: Proactive assistants continuously decide when to intervene and what context should support the intervention. Large language model (LLM) pipelines repeatedly interpret activity histories to make these decisions, paying an inference cost even when the assistant remains silent. We show that a small graph model can handle both decisions and improve the language agents it controls. Our key insight is that user activity has a native graph structure: events involve persistent entities whose recurrence connects interactions over time. Triggering and context selection map directly to predictions on event and entity nodes. We introduce a temporal-graph-learning (TGL) controller that learns these predictions jointly and supplies both outputs i